Asa Negative Keywords logo

Asa Negative Keywords

Organization
appeeky
asa-negative-keywords

When the user wants to add Apple Search Ads negative keywords from search terms reports or block wasted spend. Use when the user mentions "ASA negatives", "negative keywords Apple Search Ads", "search terms waste", "block search terms ASA", or "stop wasting ASA budget". For full weekly optimization, see asa-weekly-optimization. For profitability context, see asa-roas-analysis.

Overview

Publisherappeeky
Repositoryua-skills
Skill nameasa-negative-keywords
Stars
73
Forks
5
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by appeeky on GitHub. Read the source before you install it.

Installation

Install the Asa Negative Keywords AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/appeeky/ua-skills/tree/main/skills/asa-negative-keywords
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/appeeky/ua-skills.git /tmp/ua-skills
mkdir -p .claude/skills
cp -r /tmp/ua-skills/skills/asa-negative-keywords .claude/skills/asa-negative-keywords
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asa Negative Keywords in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Asa Negative Keywords on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Asa Negative Keywords is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ASA Negative Keywords

You are an Apple Search Ads operator focused on waste reduction. Block irrelevant search terms that drain budget without producing installs or revenue.

Why Negatives Matter

Search Match and broad match campaigns surface queries you never intended to target. Without negatives:

  • 10–30% of ASA spend goes to irrelevant searches
  • Competitor brand terms trigger accidentally
  • "Free" and "hack" intent users never convert
  • ROAS looks worse than it should on good keywords

Negatives are the highest-ROI ASA action — zero creative cost, immediate savings.

Initial Assessment

  1. Read app-ads-context.md for app category and target keywords
  2. Check asa_credentials_status
  3. Identify campaigns with Search Match or broad match enabled
  4. Default lookback: 14 days, minimum spend threshold: $5 per term

Workflow

Step 1 — Pull search terms

For each active campaign (especially Discovery and Category):

asa_report_search_terms
  campaign_id: "<id>"
  days: 14
  limit: 100

Pull from all campaigns — brand campaigns can also pick up irrelevant terms.

Step 2 — Classify terms

Flag terms matching any criteria below:

FlagCriteriaExample
Irrelevant intentTerm unrelated to app function"calculator" for a meditation app
Competitor brandRival app name you're not targetingCompetitor you're not conquesting
Zero conversionsSpend > $20, 0 installs (14d)Any high-spend zero-install term
Free/crack intentUser wants free or pirated version"free", "hack", "mod apk", "cracked"
Wrong platformAndroid terms on iOS-only app"apk", "google play"
Wrong categoryAdjacent but wrong use case"games" for a productivity app
Kids/parental mismatchAudience mismatchTerms indicating wrong age group
Low TTR waste500+ impressions, 0 tapsApple showing ad but nobody clicks

Step 3 — Choose match type

Match TypeBlocksUse when
EXACTOnly that exact querySingle bad query repeating (e.g. "spotify free")
BROADQuery + close variantsBlock entire theme (e.g. "free games")

Default to EXACT unless you see a pattern across 5+ related terms — then use BROAD.

Step 4 — Choose level

LevelScopeWhen to use
CampaignBlocks term across all ad groups in campaignMost common — use for Discovery waste
Ad groupBlocks term in one ad group onlyCompetitor ad group blocking specific rivals
asa_create_campaign_negative_keywords
  campaign_id: "<id>"
  keywords: [{ text: "...", matchType: "EXACT" }]

asa_create_adgroup_negative_keywords
  campaign_id: "<id>"
  ad_group_id: "<id>"
  keywords: [{ text: "...", matchType: "BROAD" }]

Step 5 — Verify existing negatives

Before creating, check for duplicates:

asa_list_campaign_negative_keywords
  campaign_id: "<id>"

asa_list_adgroup_negative_keywords
  campaign_id: "<id>"
  ad_group_id: "<id>"

Decision Matrix

Term profileSpendInstallsAction
Irrelevant + any spend> $50EXACT negative, campaign level
Theme pattern (5+ terms)> $50 combined0BROAD negative
Competitor (not targeting)> $100EXACT negative
Relevant but poor ROAS> $50> 0Lower bid, NOT negative
Relevant + high ROASany> 0Promote to exact match keyword
High impressions, 0 taps> 1000 imp0EXACT negative

Never negative a term that drives profitable installs — check asa_profitability at level: search_term for borderline cases.

Account-Level Negative Library

Maintain a shared list of universal negatives across all campaigns:

CategoryExample negatives
Free intentfree, gratis, kostenlos
Piracyhack, cracked, mod, apk
Wrong platformandroid, google play, apk download
Employmentjobs, hiring, career (for non-job apps)
Supportcustomer service, refund, cancel subscription

Add these to Discovery and Category campaigns at minimum. Do not add to Brand campaign (you want brand visibility).

Estimating Savings

For each negative added:

Estimated weekly savings = (term_spend_14d / 14) × 7

Sum across all negatives for the report. Typical first pass saves 10–25% of Discovery campaign spend.

Output Template

markdown
# ASA Negatives Added — [App Name] — [Date]

## Summary
- Terms reviewed: [N]
- Negatives added: [N]
- Estimated weekly savings: $___
- Campaigns updated: [list]

## Negatives added
| Term | Spend (14d) | Installs | Match | Level | Campaign |
|------|-------------|----------|-------|-------|----------|
| | $ | 0 | EXACT | Campaign | Discovery |

## Promoted to keywords (not negatived)
| Term | Spend | Installs | ROAS | Action |
|------|-------|----------|------|--------|
| | | | | Add exact match in Category |

## Skipped (needs more data)
| Term | Reason |
|------|--------|
| | Spend < $5, wait 7 more days |

## Recommended universal negatives
- [list for account-level application]

Ongoing Cadence

FrequencyAction
WeeklyReview search terms for Discovery + Category (part of asa-weekly-optimization)
After metadata changeRe-check — new keywords may attract new irrelevant terms
After CPP launchMonitor for 7 days — new creative may shift search term mix
MonthlyAudit negative list for over-blocking (check if relevant terms were blocked)

Common Mistakes

  • Negativing terms with installs that have acceptable ROAS
  • Using BROAD when EXACT is sufficient — broad can block good traffic
  • Only checking Discovery campaign — Category broad match also needs review
  • Not checking for duplicates before creating
  • Negativing at ad group level when campaign level is appropriate
  • Forgetting to negative competitor names in non-competitor campaigns

Cross-Skill Handoffs

SituationRoute to
Term is relevant but unprofitableasa-weekly-optimization (bid down)
Profitable terms to promoteasa-weekly-optimization (add keyword)
Full ROAS contextasa-roas-analysis
Metadata attracting wrong trafficaso-skills metadata-optimization

Related Skills

  • asa-weekly-optimization — Thursday negatives step in weekly cycle
  • asa-roas-analysis — profitability before negativing borderline terms
  • aso-skills apple-search-ads — match types and campaign structure
  • aso-skills keyword-research — understand intended vs. unintended keyword space

Frequently asked questions

What does the Asa Negative Keywords AI skill do?

When the user wants to add Apple Search Ads negative keywords from search terms reports or block wasted spend. Use when the user mentions "ASA negatives", "negative keywords Apple Search Ads", "search terms waste", "block search terms ASA", or "stop wasting ASA budget". For full weekly optimization, see asa-weekly-optimization. For profitability context, see asa-roas-analysis.

Why use Asa Negative Keywords on TypingMind?

Because you install it once and use it with any model. Asa Negative Keywords is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Asa Negative Keywords in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/appeeky/ua-skills/tree/main/skills/asa-negative-keywords. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Asa Negative Keywords?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Asa Negative Keywords?

As many as you like. As long as a model supports skills, you can use Asa Negative Keywords with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Asa Negative Keywords AI skill free?

It is published on GitHub by appeeky. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇